Response
Models Supporting the Response API
Icon Legend
Input: Text · Image
This page covers Azure OpenAI only
Some domestic models such as ByteDance Volcano Engine and Alibaba DashScope also support v1/responses. Refer to the rows in the Chat Models list where the endpoint column is marked v1/responses. ByteDance Volcano Engine (Ark) models support Ark's built-in web search on this endpoint — see Model Built-in Web Search → ByteDance Volcano Engine Ark.
Azure OpenAI
| Provider | API Model ID | Model Capabilities | Endpoint | Price (per 1M Tokens) | Launch Date | Expected Deprecation | Load Capacity | Supported Regions | Notes |
|---|---|---|---|---|---|---|---|---|---|
| Azure | turing/gpt-5.6-sol | max_input_tokens: 922,000max_output_tokens: 128,000Input: Output: Tools: Supported Reasoning: Supports max | v1/responsesv1/chat/completions | Input: $5Output: $30Cached Input: $0.5 | 2026-07-10 | - | Azure Global | China region Europe region North America region Asia Pacific region | GPT-5.6 flagship model; gpt-5.6 points to Sol by default |
| Azure | turing/gpt-5.6-terra | max_input_tokens: 922,000max_output_tokens: 128,000Input: Output: Tools: Supported Reasoning: Supports max | v1/responsesv1/chat/completions | Input: Output: Cached Input: | 2026-07-10 | - | Azure Global | China region Europe region North America region Asia Pacific region | GPT-5.6 balanced model, combining capability and cost efficiency |
| Azure | turing/gpt-5.6-luna | max_input_tokens: 922,000max_output_tokens: 128,000Input: Output: Tools: Supported Reasoning: Supports max | v1/responsesv1/chat/completions | Input: Output: Cached Input: | 2026-07-10 | - | Azure Global | China region Europe region North America region Asia Pacific region | GPT-5.6 fastest and most cost-effective model |
| Azure | turing/gpt-5.5 | max_input_tokens: 922,000max_output_tokens: 128,000Input: Output: Tools: Supported Reasoning: Supported | v1/responsesv1/chat/completions | Input: $5Output: $30Cached Input: $0.5 | - | - | Azure Global | China region Europe region North America region | Next-generation flagship model; Response API is recommended for reasoning |
| Azure | turing/gpt-5.4 | max_input_tokens: 922,000max_output_tokens: 128,000Input: Output: Tools: Supported Reasoning: Supported | v1/responsesv1/chat/completions | Input: $2.5Output: $15Cached Input: $0.25 | - | - | Azure Global | China region Europe region North America region | Previous-generation upgraded model; Response API is recommended for reasoning |
| Azure | turing/gpt-5.4-mini | max_input_tokens: 400,000max_output_tokens: 128,000Input: Output: Tools: Supported Reasoning: Supported | v1/responsesv1/chat/completions | Input: $0.75Output: $4.5Cached Input: $0.075 | - | - | Azure Global | China region Europe region North America region | High value-for-money mini model; Response API is recommended for reasoning |
| Azure | turing/gpt-5.4-nano | max_input_tokens: 400,000max_output_tokens: 128,000Input: Output: Tools: Supported Reasoning: Supported | v1/responsesv1/chat/completions | Input: $0.2Output: $1.25Cached Input: $0.02 | - | - | Azure Global | China region Europe region North America region | Ultra-low-cost nano model, suited for classification and sub-agent tasks |
| Azure | turing/gpt-5.3-codex | max_input_tokens: 400,000max_output_tokens: 128,000Input: Output: Tools: Supported Reasoning: Supported | v1/responses | Input: $1.75Output: $14Cached Input: $0.175 | 2026-02-26 | - | Azure Global | China region Europe region North America region | Response API only; supports reasoning tokens |
| Azure | turing/gpt-5.3-chat | max_input_tokens: 128,000max_output_tokens: 16,384Input: Output: Tools: Supported | v1/responsesv1/chat/completions | Input: $1.75Output: $14Cached Input: $0.175 | 2026-03-16 | - | Azure Global | China region Europe region North America region | |
| Azure | turing/gpt-5.2-codex | Input: Output: Tools: Supported | v1/responses | Input: $1.75Output: $14 | 2026-01-19 | - | Global | China region Europe region North America region | Response API only |
| Azure | turing/gpt-5.1 | Input: Output: Tools: Supported | v1/responsesv1/chat/completions | Input: $1.25Output: $10 | 2025-08-10 | - | Global | China region Europe region North America region | - |
| Azure | turing/gpt-5.1-chat | Input: Output: Tools: Supported | v1/responsesv1/chat/completions | Input: $1.25Output: $10 | 2025-08-10 | - | Global | China region Europe region North America region | - |
| Azure | turing/gpt-5.1-codex | Input: Output: Tools: Supported | v1/responsesv1/chat/completions | Input: $1.25Output: $10 | 2025-08-10 | - | Global | China region Europe region North America region | - |
| Azure | turing/gpt-5.1-codex-mini | Input: Output: Tools: Supported | v1/responsesv1/chat/completions | Input: $0.25Output: $2 | 2025-08-10 | - | Global | China region Europe region North America region | - |
| Azure | turing/gpt-5 | Input: Output: Tools: Supported | v1/responsesv1/chat/completions | Input: $1.25Output: $10 | 2025-08-10 | - | Global | China region Europe region North America region | - |
| Azure | turing/gpt-5-mini | Input: Output: Tools: Supported | v1/responsesv1/chat/completions | Input: $0.25Output: $2 | 2025-08-10 | - | Global | China region Europe region North America region | - |
| Azure | turing/gpt-5-nano | Input: Output: Tools: Supported | v1/responsesv1/chat/completions | Input: $0.05Output: $0.4 | 2025-08-10 | - | Global | China region Europe region North America region | - |
| Azure | turing/gpt-5-chat | Input: Output: Tools: Supported | v1/responsesv1/chat/completions | Input: $1.25Output: $10 | 2025-08-10 | - | Global | China region Europe region North America region | - |
| Azure | turing/gpt-4.1 | Input: Output: Tools: Supported | v1/responsesv1/chat/completions | Input: $2Output: $8 | 2025-04-22 | - | Global | China region Europe region North America region | - |
| Azure | turing/gpt-4.1-mini | Input: Output: Tools: Supported | v1/responsesv1/chat/completions | Input: $0.4Output: $1.6 | 2025-04-22 | - | Global | China region Europe region North America region | - |
| Azure | turing/gpt-4.1-nano | Input: Output: Tools: Supported | v1/responsesv1/chat/completions | Input: $0.1Output: $0.4 | 2025-04-22 | - | Global | China region Europe region North America region | - |
| Azure | turing/o3 | Input: Output: Tools: Supported | v1/responsesv1/chat/completions | Input: $10Output: $40 | 2025-04-17 | - | Global | China region Europe region North America region | - |
| Azure | turing/o4-mini | Input: Output: Tools: Supported | v1/responsesv1/chat/completions | Input: $1.11Output: $4.4 | 2025-04-17 | - | Global | China region Europe region North America region | - |
| Azure | turing/o3-mini | Input: Output: Tools: Supported | v1/responsesv1/chat/completions | Input: $1.11Output: $4.4 | 2025-02-19 | - | Global | China region Europe region North America region | - |
| Azure | Input: Output: Tools: Not supported | v1/responsesv1/chat/completions | Input: $15Output: $60 | 2024-09-13 | - | Global | China region Europe region North America region | - |